Prompt × gold set × models, tagged to a use case. Run a comparison to score cost, latency, and quality.
| Name | Use case | Dataset | Models |
|---|---|---|---|
| Onboarding · KYC exceptions | Digital onboarding | onboarding-kyc-gold | 2 |
| Servicing · card and EMI | Contact centre / servicing | servicing-gold | 2 |
| RM assist · policy replies | RM / wealth assist | rm-agent-gold | 2 |